ABSTRACT
PURPOSE: Deep learning techniques, including convolutional neural networks (CNN), have the potential to improve breast cancer risk prediction compared to traditional risk models. We assessed whether combining a CNN-based mammographic evaluation with clinical factors in the Breast Cancer Surveillance Consortium (BCSC) model improved risk prediction. METHODS: We conducted a retrospective cohort study among 23,467 women, age 35-74, undergoing screening mammography (2014-2018). We extracted electronic health record (EHR) data on risk factors. We identified 121 women who subsequently developed invasive breast cancer at least 1 year after the baseline mammogram. Mammograms were analyzed with a pixel-wise mammographic evaluation using CNN architecture. We used logistic regression models with breast cancer incidence as the outcome and predictors including clinical factors only (BCSC model) or combined with CNN risk score (hybrid model). We compared model prediction performance via area under the receiver operating characteristics curves (AUCs). RESULTS: Mean age was 55.9 years (SD, 9.5) with 9.3% non-Hispanic Black and 36% Hispanic. Our hybrid model did not significantly improve risk prediction compared to the BCSC model (AUC of 0.654 vs 0.624, respectively, p = 0.063). In subgroup analyses, the hybrid model outperformed the BCSC model among non-Hispanic Blacks (AUC 0.845 vs. 0.589; p = 0.026) and Hispanics (AUC 0.650 vs 0.595; p = 0.049). CONCLUSION: We aimed to develop an efficient breast cancer risk assessment method using CNN risk score and clinical factors from the EHR. With future validation in a larger cohort, our CNN model combined with clinical factors may help predict breast cancer risk in a cohort of racially/ethnically diverse women undergoing screening.
Subject(s)
Breast Neoplasms , Female , Humans , Middle Aged , Adult , Aged , Breast Neoplasms/diagnostic imaging , Breast Neoplasms/epidemiology , Mammography/methods , Retrospective Studies , Early Detection of Cancer , Neural Networks, ComputerABSTRACT
PURPOSE: The proliferation of breast epithelial cells increases during the luteal phase of the menstrual cycle, when they are exposed to progesterone, suggesting that ulipristal acetate, a selective progestin-receptor modulator (SPRM), may reduce breast cell proliferation with potential use in breast cancer chemoprevention. METHODS: Women aged 18-39 were randomized 1:1 to ulipristal 10-mg daily or to a combination oral contraceptive (COC) for 84 days. Participants underwent a breast biopsy and breast MRI at baseline and at end of study treatment. Proliferation of breast TDLU cells was evaluated by Ki67 immunohistochemical stain. We evaluated the breast MRIs for background parenchymal enhancement (BPE). All slides and images were masked for outcome evaluation. RESULTS: Twenty-eight treatment-compliant participants completed the study; 25 of whom had evaluable Ki67 results at baseline and on-treatment. From baseline to end of treatment, Ki67 % positivity (Ki67%+) decreased a median of 84% in the ulipristal group (N = 13; 2-sided p (2p) = 0.040) versus a median increase of 8% in the COC group (N = 12; 2p = 0.85). Median BPE scores decreased from 3 to 1 in the ulipristal group (p = 0.008) and did not decrease in the COC group. CONCLUSION: Ulipristal was associated with a major decrease in Ki67%+ and BPE. Ulipristal would warrant further investigation for breast cancer chemoprevention were it not for concerns about its liver toxicity. Novel SPRMs without liver toxicity could provide a new approach to breast cancer chemoprevention. TRIAL REGISTRATION: NCT02922127, 4 October 2016.
Subject(s)
Breast Neoplasms , Leiomyoma , Adolescent , Adult , Breast Neoplasms/drug therapy , Cell Proliferation , Female , Humans , Norpregnadienes , Progesterone , Receptors, Progesterone , Young AdultABSTRACT
PURPOSE: We evaluated whether a novel, fully automated convolutional neural network (CNN)-based mammographic evaluation can predict breast cancer relapse among women with operable hormone receptor (HR)-positive breast cancer. METHODS: We conducted a retrospective cohort study among women with stage I-III, HR-positive unilateral breast cancer diagnosed at Columbia University Medical Center from 2007 to 2017, who received adjuvant endocrine therapy and had at least two mammograms (baseline, annual follow-up) of the contralateral unaffected breast for CNN analysis. We extracted demographics, clinicopathologic characteristics, breast cancer treatments, and relapse status from the electronic health record. Our primary endpoint was change in CNN risk score (range, 0-1). We used two-sample t-tests to assess for difference in mean CNN scores between patients who relapsed vs. remained in remission, and conducted Cox regression analyses to assess for association between change in CNN score and breast cancer-free interval (BCFI), adjusting for known prognostic factors. RESULTS: Among 848 women followed for a median of 59 months, there were 67 (7.9%) breast cancer relapses (36 distant, 25 local, 6 new primaries). There was a significant difference in mean absolute change in CNN risk score from baseline to 1-year follow-up between those who relapsed vs. remained in remission (0.001 vs. - 0.022, p = 0.030). After adjustment for prognostic factors, a 0.01 absolute increase in CNN score at 1-year was significantly associated with BCFI, hazard ratio = 1.05 (95% Confidence Interval 1.01-1.09, p = 0.011). CONCLUSION: Short-term change in the CNN-based breast cancer risk model on adjuvant endocrine therapy predicts breast cancer relapse, and warrants further evaluation in prospective studies.
Subject(s)
Breast Neoplasms , Breast Neoplasms/diagnostic imaging , Breast Neoplasms/surgery , Female , Humans , Neoplasm Recurrence, Local/diagnostic imaging , Neural Networks, Computer , Prospective Studies , Retrospective StudiesABSTRACT
We developed a deep learning-based super-resolution model for prostate MRI. 2D T2-weighted turbo spin echo (T2w-TSE) images are the core anatomical sequences in a multiparametric MRI (mpMRI) protocol. These images have coarse through-plane resolution, are non-isotropic, and have long acquisition times (approximately 10-15 min). The model we developed aims to preserve high-frequency details that are normally lost after 3D reconstruction. We propose a novel framework for generating isotropic volumes using generative adversarial networks (GAN) from anisotropic 2D T2w-TSE and single-shot fast spin echo (ssFSE) images. The CycleGAN model used in this study allows the unpaired dataset mapping to reconstruct super-resolution (SR) volumes. Fivefold cross-validation was performed. The improvements from patch-to-volume reconstruction (PVR) to SR are 80.17%, 63.77%, and 186% for perceptual index (PI), RMSE, and SSIM, respectively; the improvements from slice-to-volume reconstruction (SVR) to SR are 72.41%, 17.44%, and 7.5% for PI, RMSE, and SSIM, respectively. Five ssFSE cases were used to test for generalizability; the perceptual quality of SR images surpasses the in-plane ssFSE images by 37.5%, with 3.26% improvement in SSIM and a higher RMSE by 7.92%. SR images were quantitatively assessed with radiologist Likert scores. Our isotropic SR volumes are able to reproduce high-frequency detail, maintaining comparable image quality to in-plane TSE images in all planes without sacrificing perceptual accuracy. The SR reconstruction networks were also successfully applied to the ssFSE images, demonstrating that high-quality isotropic volume achieved from ultra-fast acquisition is feasible.
Subject(s)
Imaging, Three-Dimensional , Prostate , Humans , Magnetic Resonance Imaging , Male , Prostate/diagnostic imagingABSTRACT
OBJECTIVE. The objective of this study was to assess the impact of artificial intelligence (AI)-based decision support (DS) on breast ultrasound (US) lesion assessment. MATERIALS AND METHODS. A multicenter retrospective review of 900 breast lesions (470/900 [52.2%] benign; 430/900 [47.8%] malignant) on US by 15 physicians (11 radiologists, two surgeons, two obstetrician/gynecologists). An AI system (Koios DS for Breast, Koios Medical) evaluated images and assigned them to one of four categories: benign, probably benign, suspicious, and probably malignant. Each reader reviewed cases twice: 750 cases with US only or with US plus DS; 4 weeks later, cases were reviewed in the opposite format. One hundred fifty additional cases were presented identically in each session. DS and reader sensitivity, specificity, and positive likelihood ratios (PLRs) were calculated as well as reader AUCs with and without DS. The Kendall τ-b correlation coefficient was used to assess intraand interreader variability. RESULTS. Mean reader AUC for cases reviewed with US only was 0.83 (95% CI, 0.78-0.89); for cases reviewed with US plus DS, mean AUC was 0.87 (95% CI, 0.84-0.90). PLR for the DS system was 1.98 (95% CI, 1.78-2.18) and was higher than the PLR for all readers but one. Fourteen readers had better AUC with US plus DS than with US only. Mean Kendall τ-b for US-only interreader variability was 0.54 (95% CI, 0.53-0.55); for US plus DS, it was 0.68 (95% CI, 0.67-0.69). Intrareader variability improved with DS; class switching (defined as crossing from BI-RADS category 3 to BI-RADS category 4A or above) occurred in 13.6% of cases with US only versus 10.8% of cases with US plus DS (p = 0.04). CONCLUSION. AI-based DS improves accuracy of sonographic breast lesion assessment while reducing inter- and intraobserver variability.
Subject(s)
Artificial Intelligence , Breast Neoplasms/diagnostic imaging , Decision Support Techniques , Ultrasonography, Mammary , Adolescent , Adult , Aged , Aged, 80 and over , Biopsy , Breast Neoplasms/pathology , Diagnosis, Computer-Assisted , Female , Humans , Middle Aged , Retrospective Studies , Sensitivity and SpecificityABSTRACT
BACKGROUND: Screening high-risk women for breast cancer with MRI is cost-effective, with increasing cost-effectiveness paralleling increasing risk. However, for average-risk women cost is considered a major limitation to mass screening with MRI. PURPOSE: To perform a cost-benefit analysis of a simulated breast cancer screening program for average-risk women comparing MRI with mammography. STUDY TYPE: Population simulation study. POPULATION/SUBJECTS: Five million (M) hypothetical women undergoing breast cancer screening. FIELD STRENGTH/SEQUENCE: Simulation based primarily on Kuhl et al8 study utilizing 1.5T MRI with an axial bilateral 2D multisection gradient-echo dynamic series (repetition time / echo time 250/4.6 msec; flip angle, 90°) with a full 512 × 512 acquisition matrix and a sensitivity encoding factor of two, performed prior to and four times after bolus injection of 0.1 mmol of gadobutrol per kg of body weight (Gadovist; Bayer, Germany). An axial T2 -weighted fast spin-echo sequence with identical anatomic parameters was also included. ASSESSMENT: A Monte Carlo simulation utilizing Medicare reimbursement rates to calculate input variable costs was developed to compare 5M women undergoing breast cancer screening with either triennial MRI or annual mammography, 2.5M in each group, over 30 years. STATISTICAL TESTS: Expected recall rates, BI-RADS 3, BI-RADS 4/5 cases and cancer detection rates were determined from published literature with calculated aggregate costs including resultant diagnostic/follow-up imaging and biopsies. RESULTS: Baseline screening of 2.5M women with breast MRI cost $1.6 billion (B), 3× higher than baseline mammography screening ($0.54B). With subsequent screening, MRI screening is more cost-effective than mammography screening in 24 years ($13.02B vs. $13.03B). MRI screening program costs are largely driven by cost per MRI exam ($549.71). A second simulation model was performed based on MRI Medicare reimbursement trends using a lower MRI cost ($400). This yielded a cost-effective benefit compared to mammography screening in less than 6 years ($3.41B vs. $3.65B), with over a 22% cost reduction relative to mammography screening in 12 years and reaching a 38% reduction in 30 years. DATA CONCLUSION: Despite higher initial cost of a breast MRI screening program for average-risk women, there is ultimately a cost savings over time compared with mammography. This estimate is conservative given cost-benefit of additional/earlier breast cancers detected by breast MRI were not accounted for. LEVEL OF EVIDENCE: 3 Technical Efficacy Stage: 6 J. Magn. Reson. Imaging 2019.
Subject(s)
Breast Neoplasms/diagnostic imaging , Breast/diagnostic imaging , Magnetic Resonance Imaging/economics , Magnetic Resonance Imaging/methods , Mammography/economics , Adult , Aged , Biopsy , Breast Neoplasms/economics , Cost-Benefit Analysis , Early Detection of Cancer/economics , Early Detection of Cancer/methods , Female , Health Care Costs , Humans , Mammography/methods , Mass Screening/economics , Mass Screening/methods , Medicare , Middle Aged , Monte Carlo Method , Risk , United StatesABSTRACT
BACKGROUND: Oncotype Dx is a validated genetic analysis that provides a recurrence score (RS) to quantitatively predict outcomes in patients who meet the criteria of estrogen receptor positive / human epidermal growth factor receptor-2 negative (ER+/HER2-)/node negative invasive breast carcinoma. Although effective, the test is invasive and expensive, which has motivated this investigation to determine the potential role of radiomics. HYPOTHESIS: We hypothesized that convolutional neural network (CNN) can be used to predict Oncotype Dx RS using an MRI dataset. STUDY TYPE: Institutional Review Board (IRB)-approved retrospective study from January 2010 to June 2016. POPULATION: In all, 134 patients with ER+/HER2- invasive ductal carcinoma who underwent both breast MRI and Oncotype Dx RS evaluation. Patients were classified into three groups: low risk (group 1, RS <18), intermediate risk (group 2, RS 18-30), and high risk (group 3, RS >30). FIELD STRENGTH/SEQUENCE: 1.5T and 3.0T. Breast MRI, T1 postcontrast. ASSESSMENT: Each breast tumor underwent 3D segmentation. In all, 1649 volumetric slices in 134 tumors (mean 12.3 slices/tumor) were evaluated. A CNN consisted of four convolutional layers and max-pooling layers. Dropout at 50% was applied to the second to last fully connected layer to prevent overfitting. Three-class prediction (group 1 vs. group 2 vs. group 3) and two-class prediction (group 1 vs. group 2/3) models were performed. STATISTICAL TESTS: A 5-fold crossvalidation test was performed using 80% training and 20% testing. Diagnostic accuracy, sensitivity, specificity, and receiver operating characteristic (ROC) area under the curve (AUC) were evaluated. RESULTS: The CNN achieved an overall accuracy of 81% (95% confidence interval [CI] ± 4%) in three-class prediction with specificity 90% (95% CI ± 5%), sensitivity 60% (95% CI ± 6%), and the area under the ROC curve was 0.92 (SD, 0.01). The CNN achieved an overall accuracy of 84% (95% CI ± 5%) in two-class prediction with specificity 81% (95% CI ± 4%), sensitivity 87% (95% CI ± 5%), and the area under the ROC curve was 0.92 (SD, 0.01). DATA CONCLUSION: It is feasible for current deep CNN architecture to be trained to predict Oncotype DX RS. LEVEL OF EVIDENCE: 4 Technical Efficacy: Stage 2 J. Magn. Reson. Imaging 2019;49:518-524.
Subject(s)
Breast Neoplasms/diagnostic imaging , Carcinoma, Ductal, Breast/diagnostic imaging , Image Processing, Computer-Assisted/methods , Magnetic Resonance Imaging , Neural Networks, Computer , Adult , Aged , Algorithms , Area Under Curve , Estrogen Receptor alpha/metabolism , Female , Humans , Imaging, Three-Dimensional , Middle Aged , Neoplasm Recurrence, Local , ROC Curve , Receptor, ErbB-2/metabolism , Reproducibility of Results , Retrospective Studies , Treatment OutcomeABSTRACT
OBJECTIVE. The purpose of this study is to evaluate the global trend in artificial intelligence (AI)-based research productivity involving radiology and its subspecialty disciplines. CONCLUSION. The United States is the global leader in AI radiology publication productivity, accounting for almost half of total radiology AI output. Other countries have increased their productivity. Notably, China has increased its productivity exponentially to close to 20% of all AI publications. The top three most productive radiology subspecialties were neuroradiology, body and chest, and nuclear medicine.
Subject(s)
Artificial Intelligence , Bibliometrics , Biomedical Research/trends , Diagnostic Imaging , Humans , Periodicals as Topic/trends , Publishing/trendsABSTRACT
OBJECTIVE. The purpose of this study was to test the hypothesis that convolutional neural networks can be used to predict which patients with pure atypical ductal hyperplasia (ADH) may be safely monitored rather than undergo surgery. MATERIALS AND METHODS. A total of 298 unique images from 149 patients were used for our convolutional neural network algorithm. A total of 134 images from 67 patients with ADH that had been diagnosed by stereotactic-guided biopsy of calcifications but had not been upgraded to ductal carcinoma in situ or invasive cancer at the time of surgical excision. A total of 164 images from 82 patients with mammographic calcifications indicated that ductal carcinoma in situ was the final diagnosis. Two standard mammographic magnification views of the calcifications (a craniocaudal view and a mediolateral or lateromedial view) were used for analysis. Calcifications were segmented using an open-source software platform and images were resized to fit a bounding box of 128 × 128 pixels. A topology with 15 hidden layers was used to implement the convolutional neural network. The network architecture contained five residual layers and dropout of 0.25 after each convolution. Patients were randomly separated into a training-and-validation set (80% of patients) and a test set (20% of patients). Code was implemented using open-source software on a workstation with an open-source operating system and a graphics card. RESULTS. The AUC value was 0.86 (95% CI, ± 0.03) for the test set. Aggregate sensitivity and specificity were 84.6% (95% CI, ± 4.0%) and 88.2% (95% CI, ± 3.0%), respectively. Diagnostic accuracy was 86.7% (95% CI, ± 2.9). CONCLUSION. It is feasible to apply convolutional neural networks to distinguish pure atypical ductal hyperplasia from ductal carcinoma in situ with the use of mammographic images. A larger dataset will likely result in further improvement of our prediction model.
ABSTRACT
The aim of this study is to develop a fully automated convolutional neural network (CNN) method for quantification of breast MRI fibroglandular tissue (FGT) and background parenchymal enhancement (BPE). An institutional review board-approved retrospective study evaluated 1114 breast volumes in 137 patients using T1 precontrast, T1 postcontrast, and T1 subtraction images. First, using our previously published method of quantification, we manually segmented and calculated the amount of FGT and BPE to establish ground truth parameters. Then, a novel 3D CNN modified from the standard 2D U-Net architecture was developed and implemented for voxel-wise prediction whole breast and FGT margins. In the collapsing arm of the network, a series of 3D convolutional filters of size 3 × 3 × 3 are applied for standard CNN hierarchical feature extraction. To reduce feature map dimensionality, a 3 × 3 × 3 convolutional filter with stride 2 in all directions is applied; a total of 4 such operations are used. In the expanding arm of the network, a series of convolutional transpose filters of size 3 × 3 × 3 are used to up-sample each intermediate layer. To synthesize features at multiple resolutions, connections are introduced between the collapsing and expanding arms of the network. L2 regularization was implemented to prevent over-fitting. Cases were separated into training (80%) and test sets (20%). Fivefold cross-validation was performed. Software code was written in Python using the TensorFlow module on a Linux workstation with NVIDIA GTX Titan X GPU. In the test set, the fully automated CNN method for quantifying the amount of FGT yielded accuracy of 0.813 (cross-validation Dice score coefficient) and Pearson correlation of 0.975. For quantifying the amount of BPE, the CNN method yielded accuracy of 0.829 and Pearson correlation of 0.955. Our CNN network was able to quantify FGT and BPE within an average of 0.42 s per MRI case. A fully automated CNN method can be utilized to quantify MRI FGT and BPE. Larger dataset will likely improve our model.
Subject(s)
Breast Neoplasms/diagnostic imaging , Image Interpretation, Computer-Assisted/methods , Imaging, Three-Dimensional/methods , Magnetic Resonance Imaging/methods , Neural Networks, Computer , Breast/diagnostic imaging , Female , Humans , Retrospective StudiesABSTRACT
To develop a convolutional neural network (CNN) algorithm that can predict the molecular subtype of a breast cancer based on MRI features. An IRB-approved study was performed in 216 patients with available pre-treatment MRIs and immunohistochemical staining pathology data. First post-contrast MRI images were used for 3D segmentation using 3D slicer. A CNN architecture was designed with 14 layers. Residual connections were used in the earlier layers to allow stabilization of gradients during backpropagation. Inception style layers were utilized deeper in the network to allow learned segregation of more complex feature mappings. Extensive regularization was utilized including dropout, L2, feature map dropout, and transition layers. The class imbalance was addressed by doubling the input of underrepresented classes and utilizing a class sensitive cost function. Parameters were tuned based on a 20% validation group. A class balanced holdout set of 40 patients was utilized as the testing set. Software code was written in Python using the TensorFlow module on a Linux workstation with one NVidia Titan X GPU. Seventy-four luminal A, 106 luminal B, 13 HER2+, and 23 basal breast tumors were evaluated. Testing set accuracy was measured at 70%. The class normalized macro area under receiver operating curve (ROC) was measured at 0.853. Non-normalized micro-aggregated AUC was measured at 0.871, representing improved discriminatory power for the highly represented Luminal A and Luminal B subtypes. Aggregate sensitivity and specificity was measured at 0.603 and 0.958. MRI analysis of breast cancers utilizing a novel CNN can predict the molecular subtype of breast cancers. Larger data sets will likely improve our model.
Subject(s)
Breast Neoplasms/pathology , Image Interpretation, Computer-Assisted/methods , Magnetic Resonance Imaging , Neural Networks, Computer , Algorithms , Female , Humans , Predictive Value of Tests , Retrospective Studies , Sensitivity and SpecificityABSTRACT
We hypothesize that convolutional neural networks (CNN) can be used to predict neoadjuvant chemotherapy (NAC) response using a breast MRI tumor dataset prior to initiation of chemotherapy. An institutional review board-approved retrospective review of our database from January 2009 to June 2016 identified 141 locally advanced breast cancer patients who (1) underwent breast MRI prior to the initiation of NAC, (2) successfully completed adriamycin/taxane-based NAC, and (3) underwent surgical resection with available final surgical pathology data. Patients were classified into three groups based on their NAC response confirmed on final surgical pathology: complete (group 1), partial (group 2), and no response/progression (group 3). A total of 3107 volumetric slices of 141 tumors were evaluated. Breast tumor was identified on first T1 postcontrast dynamic images and underwent 3D segmentation. CNN consisted of ten convolutional layers, four max-pooling layers, and dropout of 50% after a fully connected layer. Dropout, augmentation, and L2 regularization were implemented to prevent overfitting of data. Non-linear functions were modeled by a rectified linear unit (ReLU). Batch normalization was used between the convolutional and ReLU layers to limit drift of layer activations during training. A three-class neoadjuvant prediction model was evaluated (group 1, group 2, or group 3). The CNN achieved an overall accuracy of 88% in three-class prediction of neoadjuvant treatment response. Three-class prediction discriminating one group from the other two was analyzed. Group 1 had a specificity of 95.1% ± 3.1%, sensitivity of 73.9% ± 4.5%, and accuracy of 87.7% ± 0.6%. Group 2 (partial response) had a specificity of 91.6% ± 1.3%, sensitivity of 82.4% ± 2.7%, and accuracy of 87.7% ± 0.6%. Group 3 (no response/progression) had a specificity of 93.4% ± 2.9%, sensitivity of 76.8% ± 5.7%, and accuracy of 87.8% ± 0.6%. It is feasible for current deep CNN architectures to be trained to predict NAC treatment response using a breast MRI dataset obtained prior to initiation of chemotherapy. Larger dataset will likely improve our prediction model.
Subject(s)
Breast Neoplasms/diagnostic imaging , Breast Neoplasms/radiotherapy , Deep Learning , Image Interpretation, Computer-Assisted/methods , Magnetic Resonance Imaging/methods , Algorithms , Breast/diagnostic imaging , Datasets as Topic , Female , Humans , Neural Networks, Computer , Predictive Value of Tests , Retrospective Studies , Sensitivity and Specificity , Treatment OutcomeABSTRACT
OBJECTIVES: In the postneoadjuvant chemotherapy (NAC) setting, conventional radiographic complete response (rCR) is a poor predictor of pathologic complete response (pCR) of the axilla. We developed a convolutional neural network (CNN) algorithm to better predict post-NAC axillary response using a breast MRI dataset. METHODS: An institutional review board-approved retrospective study from January 2009 to June 2016 identified 127 breast cancer patients who: (1) underwent breast MRI before the initiation of NAC; (2) successfully completed Adriamycin/Taxane-based NAC; and (3) underwent surgery, including sentinel lymph node evaluation/axillary lymph node dissection with final surgical pathology data. Patients were classified into pathologic complete response (pCR) of the axilla group and non-pCR group based on surgical pathology. Breast MRI performed before NAC was used. Tumor was identified on first T1 postcontrast images underwent 3D segmentation. A total of 2811 volumetric slices of 127 tumors were evaluated. CNN consisted of 10 convolutional layers, 4 max-pooling layers. Dropout, augmentation and L2 regularization were implemented to prevent overfitting of data. RESULTS: On final surgical pathology, 38.6% (49/127) of the patients achieved pCR of the axilla (group 1), and 61.4% (78/127) of the patients did not with residual metastasis detected (group 2). For predicting axillary pCR, our CNN algorithm achieved an overall accuracy of 83% (95% confidence interval [CI] ± 5) with sensitivity of 93% (95% CI ± 6) and specificity of 77% (95% CI ± 4). Area under the ROC curve (0.93, 95% CI ± 0.04). CONCLUSIONS: It is feasible to use CNN architecture to predict post NAC axillary pCR. Larger data set will likely improve our prediction model.
Subject(s)
Algorithms , Antineoplastic Combined Chemotherapy Protocols/therapeutic use , Breast Neoplasms/pathology , Carcinoma, Ductal, Breast/pathology , Carcinoma, Lobular/pathology , Neoadjuvant Therapy , Neural Networks, Computer , Adult , Aged , Aged, 80 and over , Axilla , Biomarkers, Tumor/metabolism , Breast Neoplasms/drug therapy , Breast Neoplasms/metabolism , Carcinoma, Ductal, Breast/drug therapy , Carcinoma, Ductal, Breast/metabolism , Carcinoma, Lobular/drug therapy , Carcinoma, Lobular/metabolism , Chemotherapy, Adjuvant , Female , Follow-Up Studies , Humans , Magnetic Resonance Imaging , Middle Aged , Neoplasm Invasiveness , Prognosis , ROC Curve , Receptor, ErbB-2/metabolism , Receptors, Estrogen/metabolism , Retrospective Studies , Survival Rate , Young AdultABSTRACT
BACKGROUND: Right heart failure (RHF) after left ventricular assist device (LVAD) implantation is associated with high morbidity and mortality. Existing risk scores include semiquantitative evaluation of right ventricular (RV) dysfunction. This study aimed to determine whether quantitative evaluation of both RV size and function improve risk stratification for RHF after LVAD implantation beyond validated scores. METHODS AND RESULTS: From 2009 to 2015, 158 patients who underwent implantation of continuous-flow devices who had complete echocardiographic and hemodynamic data were included. Quantitative RV parameters included RV end-diastolic (RVEDAI) and end-systolic area index, RV free-wall longitudinal strain (RVLS), fractional area change, tricuspid annular plane systolic excursion, and right atrial area and pressure. Independent correlates of early RHF (<30 days) were determined with the use of logistic regression analysis. Mean age was 56 ± 13 years, with 79% male; 49% had INTERMACS profiles ≤2. RHF occurred in 60 patients (38%), with 20 (13%) requiring right ventricular assist device. On multivariate analysis, INTERMACS profiles (adjusted odds ratio 2.38 [95% confidence interval [CI] 1.47-3.85]), RVEDAI (1.61 [1.08-2.32]), and RVLS (2.72 [1.65-4.51]) were independent correlates of RHF (all P < .05). Both RVLS and RVEDAI were incremental to validated risk scores (including the EUROMACS score) for early RHF after LVAD (all P < .01). CONCLUSIONS: RV end-diastolic and strain are complementary prognostic markers of RHF after LVAD implantation.
Subject(s)
Heart Failure/physiopathology , Heart Ventricles/diagnostic imaging , Heart-Assist Devices , Risk Assessment/methods , Ventricular Function, Right/physiology , California/epidemiology , Disease Progression , Echocardiography , Female , Follow-Up Studies , Heart Failure/diagnosis , Heart Failure/epidemiology , Heart Ventricles/physiopathology , Humans , Incidence , Male , Middle Aged , Organ Size , Retrospective Studies , Ventricular Function, Left/physiologyABSTRACT
PURPOSE: To investigate whether the degree of breast magnetic resonance imaging (MRI) background parenchymal enhancement (BPE) is associated with the amount of breast metabolic activity measured by breast parenchymal uptake (BPU) of 18F-FDG on positron emission tomography / computed tomography (PET/CT). MATERIALS AND METHODS: An Institutional Review Board (IRB)-approved retrospective study was performed. Of 327 patients who underwent preoperative breast MRI from 1/1/12 to 12/31/15, 73 patients had 18F-FDG PET/CT evaluation performed within 1 week of breast MRI and no suspicious findings in the contralateral breast. MRI was performed on a 1.5T or 3.0T system. The imaging sequence included a triplane localizing sequence followed by sagittal fat-suppressed T2 -weighted sequence, and a bilateral sagittal T1 -weighted fat-suppressed fast spoiled gradient-echo sequence, which was performed before and three times after a rapid bolus injection (gadobenate dimeglumine, Multihance; Bracco Imaging; 0.1 mmol/kg) delivered through an IV catheter. The unaffected contralateral breast in these 73 patients underwent BPE and BPU assessments. For PET/CT BPU calculation, a 3D region of interest (ROI) was drawn around the glandular breast tissue and the maximum standardized uptake value (SUVmax ) was determined. Qualitative MRI BPE assessments were performed on a 4-point scale, in accordance with BI-RADS categories. Additional 3D quantitative MRI BPE analysis was performed using a previously published in-house technique. Spearman's correlation test and linear regression analysis was performed (SPSS, v. 24). RESULT: The median time interval between breast MRI and 18F-FDG PET/CT evaluation was 3 days (range, 0-6 days). BPU SUVmax mean value was 1.6 (SD, 0.53). Minimum and maximum BPU SUVmax values were 0.71 and 4.0. The BPU SUVmax values significantly correlated with both the qualitative and quantitative measurements of BPE, respectively (r(71) = 0.59, P < 0.001 and r(71) = 0.54, P < 0.001). Qualitatively assessed high BPE group (BI-RADS 3/4) had significantly higher BPU SUVmax of 1.9 (SD = 0.44) compared to low BPE group (BI-RADS 1/2) with an average BPU SUVmax of 1.17 (SD = 0.32) (P < 0.001). On linear regression analysis, BPU SUVmax significantly predicted qualitative and quantitative measurements of BPE (ß = 1.29, t(71) = 3.88, P < 0.001 and ß = 19.52, t(71) = 3.88, P < 0.001). CONCLUSION: There is a significant association between breast BPU and BPE, measured both qualitatively and quantitatively. Increased breast cancer risk in patients with high MRI BPE could be due to elevated basal metabolic activity of the normal breast tissue, which may provide a susceptible environment for tumor growth. LEVEL OF EVIDENCE: 3 Technical Efficacy: Stage 3 J. Magn. Reson. Imaging 2018;47:753-759.
Subject(s)
Breast/diagnostic imaging , Breast/metabolism , Fluorodeoxyglucose F18/pharmacokinetics , Imaging, Three-Dimensional/methods , Magnetic Resonance Imaging/methods , Radiopharmaceuticals/pharmacokinetics , Evaluation Studies as Topic , Female , Humans , Image Enhancement/methods , Meglumine/analogs & derivatives , Middle Aged , Organometallic Compounds , Reproducibility of Results , Retrospective StudiesABSTRACT
BACKGROUND: This study evaluated the relative accuracy of mammography, ultrasound, and magnetic resonance imaging (MRI) in predicting the tumor size of early stage breast tumors in preoperative selection of patients for intraoperative radiotherapy (IORT). METHODS: We identified 156 patients with clinical T1/T2, N0 breast cancer who underwent IORT. Clinical, pathologic, and radiation data were collected. The preoperative tumor size obtained by imaging was compared with tumor pathological size. RESULTS: The median patient age was 66. The mean tumor size at excision was 1.05 cm (0.1-3.0 cm). Out of the 156 patients, 98 had a reported, nonzero tumor size by mammography, 131 by ultrasound, and 76 by MRI. The mean difference between imaging and the tumor size was +0.062 ± 0.54 cm for mammography, -0.11 ± 0.43 cm for ultrasound, and +0.33 ± 0.55 cm for MRI, with positive values indicating an overestimate of the tumor size. MRI produced more overestimates of tumor size of at least 0.5 cm than mammography or ultrasound in a paired analysis of patients who received both modalities. CONCLUSIONS: Accuracy of imaging modalities in determining tumor size can influence patients' eligibility for IORT. Mammography and ultrasound showed acceptable accuracy in predicting size. MRI overestimated tumor size and may inappropriately exclude patients from IORT. We would discourage ruling out candidates for IORT on the basis of large size by MRI alone.
Subject(s)
Breast Neoplasms/diagnostic imaging , Breast Neoplasms/therapy , Adult , Aged , Aged, 80 and over , Breast Neoplasms/radiotherapy , Breast Neoplasms/surgery , Combined Modality Therapy , Female , Humans , Intraoperative Care/methods , Magnetic Resonance Imaging/methods , Mammography/methods , Middle Aged , Neoplasm Staging , Radiotherapy Planning, Computer-Assisted , Retrospective Studies , Ultrasonography, Mammary/methodsABSTRACT
OBJECTIVE: The purpose of this article is to report on a study conducted to determine whether the lesions in patients with what is deemed to be low-risk ductal carcinoma in situ (DCIS) selected for two large clinical trials are in fact low-risk lesions. CONCLUSION: A retrospective review was conducted to determine whether the eligibility criteria of the two trials are predictive that DCIS is low risk. More than 20% of lesions are upgraded to invasive carcinoma in patients with low-risk DCIS as defined in two large clinical trials. More accurate methods are needed to determine whether patients with a diagnosis of low-grade DCIS can be treated less aggressively.
Subject(s)
Breast Neoplasms/diagnostic imaging , Breast Neoplasms/pathology , Carcinoma, Intraductal, Noninfiltrating/diagnostic imaging , Carcinoma, Intraductal, Noninfiltrating/pathology , Patient Selection , Female , Humans , Neoplasm Grading , Observational Studies as Topic , Retrospective StudiesABSTRACT
SAVI SCOUT Surgical Guidance System has been shown to be a reliable and safe alternative to wire localization in breast surgery. This study evaluated the feasibility of using multiple reflectors in the same breast. We performed an IRB-approved, HIPAA-compliant, single-institution retrospective review of 183 patients who underwent breast lesion localization and excision using SAVI SCOUT Surgical Guidance System (Cianna Medical) between June 2015 and January 2017. We performed a subset analysis in 42 patients in whom more than one reflector was placed. Specimen radiography, pathology, distance between reflectors, target removal, margin positivity, and complications were evaluated. Among 183 patients, 42 patients had more than one reflector placed in the same breast to localize 68 lesions. Benign (n = 6, 8.8%), high-risk (n = 23, 33.8%), and malignant (n = 39, 57.4%) lesions were included. Thirty-six patients (85.7%) had a total of 2 reflectors placed and 6 patients had a total of 3 reflectors placed (14.3%). The indications for multiple reflector placement in the same breast included multiple separate lesions (n = 23) and bracketing of large lesions (n = 19). The mean distance between the reflectors was 42 mm (22-93 mm). All lesions were successfully targeted and retrieved. Of 39 malignant lesions, 10.3% (n = 4) had positive margins and 10.3% (n = 4) had close (<1 mm) margins at surgery. All patients with positive margins underwent re-excision. No complications occurred preoperatively, intra-operatively, or postoperatively. The use of multiple SAVI SCOUT reflectors for localizing multiple lesions in the same breast or bracketing large lesions is feasible and safe.
Subject(s)
Breast Neoplasms/pathology , Mastectomy, Segmental/methods , Breast Neoplasms/diagnostic imaging , Breast Neoplasms/surgery , Feasibility Studies , Female , Humans , Margins of Excision , Retrospective StudiesABSTRACT
INTRODUCTION: The planned use of a temporary right ventricular assist device (RVAD) at the time of left ventricular assist device (LVAD) implantation may prevent the need for a permanent biventricular assist device (BiVAD). Herein we describe our RVAD weaning protocol that was effectively employed in 4 patients to prevent the need for permanent BiVAD. METHODS: Four patients in refractory cardiogenic shock underwent planned RVAD insertion during LVAD implantation due to severely depressed right ventricular function with dilation preoperatively. A standardized RVAD weaning protocol was employed in these 4 patients in preparation for decannulation. RESULTS: Temporary RVADs were successfully placed in all 4 patients at the time of LVAD implantation. All patients survived to RVAD decannulation and discharge and were alive at the time of most recent follow-up (range, 528-742 days post-RVAD decannulation). CONCLUSION: Planned implantation of a temporary RVAD in high risk patients may avoid the need for biventricular mechanical support in the future.
Subject(s)
Heart Ventricles/surgery , Heart-Assist Devices , Shock, Cardiogenic/surgery , Ventricular Function, Left/physiology , Ventricular Function, Right/physiology , Adult , Echocardiography, Transesophageal , Follow-Up Studies , Humans , Male , Middle Aged , Retrospective Studies , Shock, Cardiogenic/diagnosisABSTRACT
The aim of this study is to evaluate the role of convolutional neural network (CNN) in predicting axillary lymph node metastasis, using a breast MRI dataset. An institutional review board (IRB)-approved retrospective review of our database from 1/2013 to 6/2016 identified 275 axillary lymph nodes for this study. Biopsy-proven 133 metastatic axillary lymph nodes and 142 negative control lymph nodes were identified based on benign biopsies (100) and from healthy MRI screening patients (42) with at least 3 years of negative follow-up. For each breast MRI, axillary lymph node was identified on first T1 post contrast dynamic images and underwent 3D segmentation using an open source software platform 3D Slicer. A 32 × 32 patch was then extracted from the center slice of the segmented tumor data. A CNN was designed for lymph node prediction based on each of these cropped images. The CNN consisted of seven convolutional layers and max-pooling layers with 50% dropout applied in the linear layer. In addition, data augmentation and L2 regularization were performed to limit overfitting. Training was implemented using the Adam optimizer, an algorithm for first-order gradient-based optimization of stochastic objective functions, based on adaptive estimates of lower-order moments. Code for this study was written in Python using the TensorFlow module (1.0.0). Experiments and CNN training were done on a Linux workstation with NVIDIA GTX 1070 Pascal GPU. Two class axillary lymph node metastasis prediction models were evaluated. For each lymph node, a final softmax score threshold of 0.5 was used for classification. Based on this, CNN achieved a mean five-fold cross-validation accuracy of 84.3%. It is feasible for current deep CNN architectures to be trained to predict likelihood of axillary lymph node metastasis. Larger dataset will likely improve our prediction model and can potentially be a non-invasive alternative to core needle biopsy and even sentinel lymph node evaluation.